46 lines
895 B
Markdown
46 lines
895 B
Markdown
---
|
|
base_model: []
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Merged_Qwen2-0.5B_0.3
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
## Merge Details
|
|
### Merge Method
|
|
|
|
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using /kaggle/working/Qwen2-0.5B as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* /kaggle/working/debias_Qwen2-0.5B
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
base_model: /kaggle/working/Qwen2-0.5B
|
|
dtype: float32
|
|
merge_method: della
|
|
models:
|
|
- model: /kaggle/working/debias_Qwen2-0.5B
|
|
parameters:
|
|
density: 0.5
|
|
epsilon: 0.1
|
|
weight: 1.0
|
|
parameters:
|
|
int8_mask: true
|
|
lambda: 0.3
|
|
normalize: true
|
|
rescale: true
|
|
tokenizer:
|
|
source: /kaggle/working/Qwen2-0.5B
|
|
|
|
```
|